{"id":"https://openalex.org/W4404782435","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.683","title":"GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text","display_name":"GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782435","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.683"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.683","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.emnlp-main.683","pdf_url":"https://aclanthology.org/2024.emnlp-main.683.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.emnlp-main.683.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037363867","display_name":"Michael Ginn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Ginn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092050382","display_name":"Lindia Tjuatja","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lindia Tjuatja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087688208","display_name":"Taiqi He","orcid":"https://orcid.org/0000-0002-7122-3493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taiqi He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114139663","display_name":"Enora Rice","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enora Rice","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069931383","display_name":"Alexis Palmer","orcid":"https://orcid.org/0000-0001-5071-3090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Palmer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008257790","display_name":"Lori Levin","orcid":"https://orcid.org/0000-0003-0831-3063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lori Levin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58779028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12267","last_page":"12286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8031036853790283},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6519646644592285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354336500167847},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5020871162414551},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.07975885272026062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031036853790283},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6519646644592285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354336500167847},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5020871162414551},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.07975885272026062}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.683","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.emnlp-main.683","pdf_url":"https://aclanthology.org/2024.emnlp-main.683.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.683","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.emnlp-main.683","pdf_url":"https://aclanthology.org/2024.emnlp-main.683.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G1581117376","display_name":"Collaborative Research: RI: Medium: From Acoustic Signal to Morphosyntactic Analysis in One End-to-End Neural System","funder_award_id":"2211951","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782435.pdf","grobid_xml":"https://content.openalex.org/works/W4404782435.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W1970433854","https://openalex.org/W4396701345","https://openalex.org/W2023867642","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Language":[0],"documentation":[1,114],"projects":[2],"often":[3],"involve":[4],"the":[5,60,104,132],"creation":[6],"of":[7,36,64,70,90,98,106,134],"annotated":[8],"text":[9,17],"in":[10,24,56,110],"a":[11,25,68,95,124],"format":[12],"such":[13,54],"as":[14],"interlinear":[15],"glossed":[16],"(IGT),":[18],"which":[19],"captures":[20],"fine-grained":[21],"morphosyntactic":[22],"analyses":[23],"morpheme-by-morpheme":[26],"format.However,":[27],"there":[28],"are":[29,154],"few":[30],"existing":[31,62],"resources":[32],"providing":[33],"large":[34,125],"amounts":[35],"standardized,":[37],"easily":[38],"accessible":[39],"IGT":[40,65,86,109],"data,":[41,121],"limiting":[42],"their":[43],"applicability":[44],"to":[45,52,79,93,112,148],"linguistic":[46],"research,":[47],"and":[48,85,152],"making":[49],"it":[50,139],"difficult":[51],"use":[53],"data":[55,66,92],"NLP":[57],"modeling.We":[58],"compile":[59],"largest":[61],"corpus":[63],"from":[67],"variety":[69],"sources,":[71],"covering":[72],"over":[73],"450k":[74],"examples":[75],"across":[76,100],"1.8k":[77],"languages,":[78],"enable":[80],"research":[81],"on":[82,128,140,156],"crosslingual":[83],"transfer":[84],"generation.We":[87],"normalize":[88],"much":[89],"our":[91,129],"follow":[94],"standard":[96],"set":[97],"labels":[99],"languages.Furthermore,":[101],"we":[102,122],"explore":[103],"task":[105],"automatically":[107],"generating":[108],"order":[111],"aid":[113],"projects.As":[115],"many":[116],"languages":[117],"lack":[118],"sufficient":[119],"monolingual":[120,141],"pretrain":[123],"multilingual":[126],"model":[127,136,151],"corpus.We":[130],"demonstrate":[131],"utility":[133],"this":[135],"by":[137,146],"finetuning":[138],"corpora,":[142],"outperforming":[143],"SOTA":[144],"models":[145],"up":[147],"6.6%.Our":[149],"pretrained":[150],"dataset":[153],"available":[155],"Hugging":[157],"Face.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}